一种高效的基于复制的联邦学习聚合验证和正确性保证方案

IF 5.5 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Shihong Wu;Yuchuan Luo;Shaojing Fu;Yingwen Chen;Ming Xu
{"title":"一种高效的基于复制的联邦学习聚合验证和正确性保证方案","authors":"Shihong Wu;Yuchuan Luo;Shaojing Fu;Yingwen Chen;Ming Xu","doi":"10.1109/TSC.2024.3520833","DOIUrl":null,"url":null,"abstract":"Federated learning(FL), enabling multiple clients collaboratively to train a model via a parameter server, is an effective approach to address the issue of data silos. However, due to the self-interest and laziness of servers, they may not correctly aggregate the global model parameters, which will cause the final model trained to deviate from the training goal. In the existing proposals, the cryptography-based verification scheme involves heavy computation overheads. On the other hand, the replication-based verification method, relying on a dual-server architecture, can ensure the correctness of aggregation and reduce computation overheads, but incur at least twice the communication cost as that of the task itself. To address these issues, we propose a novel replication-based aggregation scheme for FL, which enables efficient verification and stronger correctness assurance. The scheme employs a main-secondary server architecture, which allows the secondary servers to partakes in aggregation tasks at a predetermined probability, consequently mitigating the validation overhead. Moreover, we resort to the game theory and design a Learning Contract to impose penalties on dishonest servers, enforcing rational servers to correctly compute global model parameters. Under the use of Betrayal Contract to prevent collusion among servers, we further design a training game to efficiently verify global model parameters and ensure their correctness. Finally, we analyze the correctness of the proposed scheme and demonstrate that the computational overhead of our scheme is <inline-formula><tex-math>$\\frac{{n + 1}}{{2n}}$</tex-math></inline-formula> of the previous replication-based validation scheme, obtaining a significant reduction in communication cost, where <inline-formula><tex-math>$n$</tex-math></inline-formula> means the training rounds. Experimental results further validate our deduction.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"633-646"},"PeriodicalIF":5.5000,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Efficient Replication-Based Aggregation Verification and Correctness Assurance Scheme for Federated Learning\",\"authors\":\"Shihong Wu;Yuchuan Luo;Shaojing Fu;Yingwen Chen;Ming Xu\",\"doi\":\"10.1109/TSC.2024.3520833\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Federated learning(FL), enabling multiple clients collaboratively to train a model via a parameter server, is an effective approach to address the issue of data silos. However, due to the self-interest and laziness of servers, they may not correctly aggregate the global model parameters, which will cause the final model trained to deviate from the training goal. In the existing proposals, the cryptography-based verification scheme involves heavy computation overheads. On the other hand, the replication-based verification method, relying on a dual-server architecture, can ensure the correctness of aggregation and reduce computation overheads, but incur at least twice the communication cost as that of the task itself. To address these issues, we propose a novel replication-based aggregation scheme for FL, which enables efficient verification and stronger correctness assurance. The scheme employs a main-secondary server architecture, which allows the secondary servers to partakes in aggregation tasks at a predetermined probability, consequently mitigating the validation overhead. Moreover, we resort to the game theory and design a Learning Contract to impose penalties on dishonest servers, enforcing rational servers to correctly compute global model parameters. Under the use of Betrayal Contract to prevent collusion among servers, we further design a training game to efficiently verify global model parameters and ensure their correctness. Finally, we analyze the correctness of the proposed scheme and demonstrate that the computational overhead of our scheme is <inline-formula><tex-math>$\\\\frac{{n + 1}}{{2n}}$</tex-math></inline-formula> of the previous replication-based validation scheme, obtaining a significant reduction in communication cost, where <inline-formula><tex-math>$n$</tex-math></inline-formula> means the training rounds. Experimental results further validate our deduction.\",\"PeriodicalId\":13255,\"journal\":{\"name\":\"IEEE Transactions on Services Computing\",\"volume\":\"18 2\",\"pages\":\"633-646\"},\"PeriodicalIF\":5.5000,\"publicationDate\":\"2025-04-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Services Computing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10963996/\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Services Computing","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10963996/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

联邦学习(FL)是解决数据孤岛问题的一种有效方法,它允许多个客户机通过参数服务器协作训练模型。然而,由于服务器的自身利益和懒惰,它们可能无法正确地聚合全局模型参数,从而导致最终训练出的模型偏离训练目标。在现有的方案中,基于密码学的验证方案涉及大量的计算开销。另一方面,基于复制的验证方法依赖于双服务器架构,可以保证聚合的正确性,减少计算开销,但产生的通信成本至少是任务本身的两倍。为了解决这些问题,我们提出了一种新的基于复制的FL聚合方案,该方案能够实现高效的验证和更强的正确性保证。该方案采用主从服务器架构,允许辅助服务器以预定的概率参与聚合任务,从而减少验证开销。此外,我们利用博弈论,设计了一个学习契约来对不诚实的服务器施加惩罚,强制理性服务器正确计算全局模型参数。在利用背叛契约防止服务器间串通的情况下,我们进一步设计了一个训练游戏,以有效地验证全局模型参数并保证其正确性。最后,我们分析了所提出方案的正确性,并证明了该方案的计算开销是先前基于复制的验证方案的$\frac{{n + 1}}{{2n}}$,显著降低了通信成本,其中$n$表示训练轮数。实验结果进一步验证了我们的推断。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
An Efficient Replication-Based Aggregation Verification and Correctness Assurance Scheme for Federated Learning
Federated learning(FL), enabling multiple clients collaboratively to train a model via a parameter server, is an effective approach to address the issue of data silos. However, due to the self-interest and laziness of servers, they may not correctly aggregate the global model parameters, which will cause the final model trained to deviate from the training goal. In the existing proposals, the cryptography-based verification scheme involves heavy computation overheads. On the other hand, the replication-based verification method, relying on a dual-server architecture, can ensure the correctness of aggregation and reduce computation overheads, but incur at least twice the communication cost as that of the task itself. To address these issues, we propose a novel replication-based aggregation scheme for FL, which enables efficient verification and stronger correctness assurance. The scheme employs a main-secondary server architecture, which allows the secondary servers to partakes in aggregation tasks at a predetermined probability, consequently mitigating the validation overhead. Moreover, we resort to the game theory and design a Learning Contract to impose penalties on dishonest servers, enforcing rational servers to correctly compute global model parameters. Under the use of Betrayal Contract to prevent collusion among servers, we further design a training game to efficiently verify global model parameters and ensure their correctness. Finally, we analyze the correctness of the proposed scheme and demonstrate that the computational overhead of our scheme is $\frac{{n + 1}}{{2n}}$ of the previous replication-based validation scheme, obtaining a significant reduction in communication cost, where $n$ means the training rounds. Experimental results further validate our deduction.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEEE Transactions on Services Computing
IEEE Transactions on Services Computing COMPUTER SCIENCE, INFORMATION SYSTEMS-COMPUTER SCIENCE, SOFTWARE ENGINEERING
CiteScore
11.50
自引率
6.20%
发文量
278
审稿时长
>12 weeks
期刊介绍: IEEE Transactions on Services Computing encompasses the computing and software aspects of the science and technology of services innovation research and development. It places emphasis on algorithmic, mathematical, statistical, and computational methods central to services computing. Topics covered include Service Oriented Architecture, Web Services, Business Process Integration, Solution Performance Management, and Services Operations and Management. The transactions address mathematical foundations, security, privacy, agreement, contract, discovery, negotiation, collaboration, and quality of service for web services. It also covers areas like composite web service creation, business and scientific applications, standards, utility models, business process modeling, integration, collaboration, and more in the realm of Services Computing.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信